Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 103813
    Prev
    Next
    INDEX
    Explanations

    one-time services

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ━━━━━━━━━━━━━━━━
    -0.07
     Teresa
    -0.07
    克
    -0.07
     contracts
    -0.06
    ________
    -0.06
    PERT
    -0.06
    Contracts
    -0.06
    .mount
    -0.06
    dif
    -0.06
    _execute
    -0.06
    POSITIVE LOGITS
     Indies
    0.07
     Jako
    0.07
     мая
    0.07
    роиз
    0.07
     ni
    0.07
    і
    0.06
    第一次
    0.06
     влас
    0.06
     Μη
    0.06
    -buy
    0.06
    Activations Density 0.095%

    No Known Activations